INDEX

Explanations

conversations about identity and personal experiences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Japanese sentence fragments

np_acts-logits-general · gemini-2.0-flash

what are you doing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.98

ſelf

-0.94

 myſelf

-0.89

 auffi

-0.82

 sahiptir

-0.82

 iſt

-0.81

 ―――――

-0.81

 ―――

-0.80

 pleaſure

-0.79

ſelves

-0.79

POSITIVE LOGITS

 really

1.03

 pretty

0.99

 guys

0.89

 nice

0.89

 weird

0.86

 shit

0.85

 fucking

0.84

 REALLY

0.82

 like

0.82

 Really

0.81

Activations Density 0.197%

conversations about identity and personal experiences

Japanese sentence fragments

what are you doing

No Comments

No Known Activations